© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 571
    Prev
    Next
    INDEX
    Explanations

    amber

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.37
     "
    -0.56
    '
    -0.56
     di
    -0.54
     continúas
    -0.50
     '
    -0.50
    mockito
    -0.50
     “
    -0.49
     at
    -0.48
    ’
    -0.48
    POSITIVE LOGITS
     purpoſe
    0.92
     myſelf
    0.90
     Reſ
    0.82
     pleaſure
    0.81
     houſe
    0.80
     itſelf
    0.79
     leſs
    0.79
     ſta
    0.77
     Majefty
    0.77
     ſtate
    0.76
    Activations Density 0.007%

    No Known Activations